From 1c6d9582d0d8e1963afc9123baeac0898e35362d Mon Sep 17 00:00:00 2001
From: Olamide Israel <olamide@omicmd.com>
Date: Fri, 14 Mar 2025 10:46:31 -0700
Subject: [PATCH] Add Nextflow pipeline for PROPKA with Docker configuration

---
 Dockerfile      | 23 +++++++++++++++++
 main.nf         | 30 +++++++++++++++++++++
 nextflow.config | 37 ++++++++++++++++++++++++++
 params.json     | 69 +++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 159 insertions(+)
 create mode 100644 Dockerfile
 create mode 100644 main.nf
 create mode 100644 nextflow.config
 create mode 100644 params.json

diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..2c09442
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,23 @@
+FROM python:3.10-slim-bullseye
+
+# Update and install basic utilities and dependencies
+RUN apt-get update -y \
+    && apt-get -y upgrade --fix-missing \
+    && apt-get -y install git procps coreutils \
+                          build-essential \
+                          gcc \
+                          python3-dev \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /workspace
+
+# Install PROPKA with dependencies 
+RUN pip install --no-cache-dir numpy pytest \
+    && pip install --no-cache-dir propka
+
+# Make propka3 available in PATH (should already be in path from pip install)
+ENV PATH="/usr/local/bin:${PATH}"
+
+# Test that the installation worked
+RUN propka3 --help
diff --git a/main.nf b/main.nf
new file mode 100644
index 0000000..c11293d
--- /dev/null
+++ b/main.nf
@@ -0,0 +1,30 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl=2
+
+params.pdb = "/mnt/OmicNAS/private/old/olamide/propka/input/1HPX.pdb"
+params.outdir = "/mnt/OmicNAS/private/old/olamide/propka/output"
+params.ph = 7.0
+params.options = ""
+
+process PROPKA {
+    container 'propka:latest'
+    publishDir params.outdir, mode: 'copy'
+    
+    input:
+        path pdb
+    
+    output:
+        path "${pdb.baseName}.pka", emit: pka_file
+        path "run.log"
+    
+    script:
+        """
+        propka3 ${params.options} --pH ${params.ph} ${pdb} 2>&1 | tee run.log
+        """
+}
+
+workflow {
+    pdb_files = Channel.fromPath(params.pdb)
+    PROPKA(pdb_files)
+}
diff --git a/nextflow.config b/nextflow.config
new file mode 100644
index 0000000..bdf4600
--- /dev/null
+++ b/nextflow.config
@@ -0,0 +1,37 @@
+// Manifest for Nextflow metadata
+manifest {
+    name = 'PROPKA-Nextflow'
+    author = 'Generated from PROPKA repository'
+    homePage = 'https://github.com/jensengroup/propka'
+    description = 'Nextflow pipeline for PROPKA - Empirical pKa prediction for proteins and protein-ligand complexes'
+    mainScript = 'main.nf'
+    version = '1.0.0'
+}
+
+// Global default parameters
+params {
+    pdb = "/mnt/OmicNAS/private/old/olamide/propka/input/1HPX.pdb"
+    outdir = "/mnt/OmicNAS/private/old/olamide/propka/output"
+    ph = 7.0
+    options = ""
+}
+
+// Container configurations
+docker {
+    enabled = true
+    runOptions = ''
+}
+
+// Process configurations
+process {
+    cpus = 1
+    memory = '4 GB'
+}
+
+// Execution configurations
+executor {
+    $local {
+        cpus = 2
+        memory = '4 GB'
+    }
+}
diff --git a/params.json b/params.json
new file mode 100644
index 0000000..aed0259
--- /dev/null
+++ b/params.json
@@ -0,0 +1,69 @@
+{
+    "params": {
+        "pdb": {
+            "type": "file",
+            "description": "Path pattern to PDB files for pKa prediction",
+            "default": "/mnt/OmicNAS/private/old/olamide/propka/input/1HPX.pdb",
+            "required": true,
+            "pipeline_io": "input",
+            "var_name": "params.pdb",
+            "examples": [
+                "/mnt/OmicNAS/private/old/olamide/propka/input/protein.pdb",
+                "/mnt/OmicNAS/private/old/olamide/propka/input/*.pdb"
+            ],
+            "pattern": ".*\\.pdb$",
+            "enum": [],
+            "validation": {},
+            "notes": "Can be a single PDB file or a pattern to match multiple PDB files."
+        },
+        "outdir": {
+            "type": "folder",
+            "description": "Directory for PROPKA prediction results",
+            "default": "/mnt/OmicNAS/private/old/olamide/propka/output",
+            "required": true,
+            "pipeline_io": "output",
+            "var_name": "params.outdir",
+            "examples": [
+                "/mnt/OmicNAS/private/old/olamide/propka/output",
+                "/path/to/custom/output"
+            ],
+            "pattern": ".*",
+            "enum": [],
+            "validation": {},
+            "notes": "Directory where pKa prediction results will be stored. Will be created if it doesn't exist."
+        },
+        "ph": {
+            "type": "number",
+            "description": "pH value for titration calculations",
+            "default": 7.0,
+            "required": false,
+            "pipeline_io": "parameter",
+            "var_name": "params.ph",
+            "examples": [
+                7.0,
+                5.5
+            ],
+            "validation": {
+                "min": 0.0,
+                "max": 14.0
+            },
+            "notes": "The pH value used for calculating residue protonation states."
+        },
+        "options": {
+            "type": "string",
+            "description": "Additional command-line options for PROPKA",
+            "default": "",
+            "required": false,
+            "pipeline_io": "parameter",
+            "var_name": "params.options",
+            "examples": [
+                "--titrate_only Asp,Glu",
+                "--window 1.0"
+            ],
+            "pattern": ".*",
+            "enum": [],
+            "validation": {},
+            "notes": "Additional command-line options to pass to propka3. See propka3 --help for available options."
+        }
+    }
+}